Coding Test Javier Botero

.gitignore

@@ -10,6 +10,9 @@
 /test/version_tmp/
 /tmp/
 
+# byebug history
+.byebug_history
+
 # Used by dotenv library to load environment variables.
 # .env
 

Gemfile

@@ -0,0 +1,11 @@
+source 'https://rubygems.org'
+
+gem 'httparty'
+gem 'nokogiri'
+
+group :test do
+  gem 'rspec'
+  gem "webmock"
+end
+
+gem "byebug", "~> 12.0", :groups => [:development, :test]

Gemfile.lock

@@ -0,0 +1,57 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    addressable (2.8.7)
+      public_suffix (>= 2.0.2, < 7.0)
+    bigdecimal (3.1.9)
+    byebug (12.0.0)
+    crack (1.0.0)
+      bigdecimal
+      rexml
+    csv (3.3.4)
+    diff-lcs (1.6.1)
+    hashdiff (1.1.2)
+    httparty (0.23.1)
+      csv
+      mini_mime (>= 1.0.0)
+      multi_xml (>= 0.5.2)
+    mini_mime (1.1.5)
+    mini_portile2 (2.8.8)
+    multi_xml (0.7.1)
+      bigdecimal (~> 3.1)
+    nokogiri (1.18.8)
+      mini_portile2 (~> 2.8.2)
+      racc (~> 1.4)
+    public_suffix (6.0.1)
+    racc (1.8.1)
+    rexml (3.4.1)
+    rspec (3.13.0)
+      rspec-core (~> 3.13.0)
+      rspec-expectations (~> 3.13.0)
+      rspec-mocks (~> 3.13.0)
+    rspec-core (3.13.3)
+      rspec-support (~> 3.13.0)
+    rspec-expectations (3.13.3)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-mocks (3.13.2)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.2)
+    webmock (3.25.1)
+      addressable (>= 2.8.0)
+      crack (>= 0.3.2)
+      hashdiff (>= 0.4.0, < 2.0.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  byebug (~> 12.0)
+  httparty
+  nokogiri
+  rspec
+  webmock
+
+BUNDLED WITH
+   2.1.4

files/body_parser.rb

@@ -0,0 +1,55 @@
+require 'httparty'
+require 'nokogiri'
+require 'json'
+
+class BodyParser
+  attr_reader :query, :url, :document, :images
+
+  def initialize(url)
+    @url = url
+  end
+
+  def call
+    begin
+      response = HTTParty.get(url)
+      if response.success?
+        @document = Nokogiri::HTML(response.body)
+        @images = { artworks: get_images }.to_json
+      else
+        warn "HTTP Error fetching #{url}: #{response.code}"
+      end
+    rescue StandardError => e
+      warn "Error fetching or parsing: #{e.message}"
+      self.document = nil
+      self.images = nil
+    end
+  end
+
+  private
+
+  def get_images
+    candidate_images = document.css('a > img')
+    extract_data(candidate_images)
+  end
+
+  def extract_data(candidate_images)
+    candidate_images.map do |image|
+      anchor = image.parent
+      next unless anchor && anchor.name == 'a' && anchor['href'].match(/\/search\?/)
+
+      div = anchor.css('div').first
+      next unless div && div.name == 'div'
+
+      extensions = div.children
+                      .map(&:text)
+                      .select{ |ext| ext.match(/\d{4}/) }
+
+      {
+        name: image['alt'],
+        extensions: extensions.any? ? extensions : nil,
+        link: "https://www.google.com#{anchor['href']}",
+        image: image['src']
+      }
+    end.compact
+  end
+end